A System and a Method for Image Recognition

1. An image recognition system, comprising: a robot, having an image collection module, configured to drive the image collection module to collect an image in a view of the robot by an image collection drive module; a light source configured to emit light only while the image collection module is collecting an image; a face detection module configured to locate a face image in the image collected by the image collection module; a face recognition module configured to implement a preprocessing for the located face image, then the preprocessed face image being compared with an image feature information of a known identity contained in a database, to determine an identity information and a confidence probability of the face image; wherein, the database comprises: a local data memory module that adopts a face recognition technology according to a feature matching; wherein firstly, the local data memory module makes a feature database of the face image of the known identity; secondly, it extracts a same type of feature according to the face image of a real-time collection, comparing a feature distance of a present face to a feature distance of a database face through a math distance function; finally, it determines a possible identity, and gives out the confidence probability; and a web server data memory module, wherein the web server data memory module adopts the face recognition technology based on a deep learning model which is configured to generate a face feature in the database, to construct a face category in the database by support vector machine (SVM) algorithm or other standard classifiers; then the web server data memory module having computing resources calculates a model feature according to the face image of the real-time collection, and determines the possible identity and confidence probability of the face image by the classifier.

2. The image recognition system as claimed in claim 1 , wherein the image collection module is a high definition camera, the high definition camera is configured to collect a static image and to collect at least 30 frames per second of video; and wherein the high definition camera is connected to the robot by a mobile industry processor interface (MIPI) or a universal serial bus (USB) interface.

3. The image recognition system as claimed in claim 1 , wherein the light source comprises an ambient light source and an infrared light source; and wherein upon utilizing the ambient light to emit light and collecting the image by the image collection module, if the collected image can not be recognized, light is emitted by the infrared light source.

4. The image recognition system as claimed in claim 1 , the preprocessing comprising: executing an angle correction treatment and a light treatment for the face image presenting in the image.

5. The image recognition system as claimed in claim 1 , wherein the robot further comprises a sounding device connected to the database, wherein the sounding device sends out various types of prompt tones according to a comparative result from the face recognition module.

6. The image recognition system as claimed in claim 1 , further comprising a record feedback device to record and/or feed back a comparative result from the face recognition module.

7. The image recognition system as claimed in claim 1 , wherein the face recognition module implements a comparison by the SVM algorithm.

8. An image recognition method, using an image recognition system comprising: a robot having an image collection module, configured to drive the image collection module to collect an image in a view of the robot by an image collection drive module; a light source configured to emit light only while the image collection module is collecting an image; a face detection module configured to locate a face image in the image collected by the image collection module; and a face recognition module configured to implement a preprocessing for the located face image, then the preprocessed face image being compared with an image feature information of a known identity contained in a database, to determine an identity information and a confidence probability of the face image; wherein the method comprises the steps of: (a) collecting the image in the view of the robot by the image collection module of the robot while emitting light by the light source only while collecting the image; (b) using the face detection module to implement a location process to the face image presenting in the image which is collected by the image collection module; (c) using the face detection module to implement a preprocessing for the face image after being located, then comparing with the image feature information of the known identity contained in the database, to determine the identity information and the confidence probability of the face image, by: adopting, by a local data memory module, a face recognition technology according to a feature matching, by: making, by the local data memory module, a feature database of the face image of the known identity; extracting a same type of feature according to the face image of a real-time collection; comparing a feature distance of a present face to a feature distance of a database face through a math distance function; determining a possible identity, and giving out the confidence probability; adopting, by a web server data memory module, the face recognition technology based on a deep learning model, which is configured to generate a face feature in the database, to construct a face category in the database by support vector machine (SVM) algorithm or other standard classifiers; calculating, via computing resources in the web server data memory module, a model feature according to the face image of the real-time collection; and determining the possible identity and confidence probability of the face image by the classifier.

9. The image recognition method as claimed in claim 8 , wherein the image collection module is a high definition camera, the high definition camera is configured to collect a static image and collect at least 30 frames per second of video; and wherein the high definition camera is connected to the robot by a mobile industry processor interface (MIPI) or a universal serial bus (USB) interface.

10. The image recognition method as claimed in claim 8 , wherein the light source comprises an ambient light source and an infrared light source; and wherein upon utilizing the ambient light to emit light and collecting the image by the image collection module, if the collected image can not be recognized, light is emitted by the infrared light source.

11. The image recognition method as claimed in claim 8 , the preprocessing comprising: executing an angle correction treatment and a light treatment for the face image presenting in the image.

12. The image recognition method as claimed in claim 8 , wherein the robot further comprises a sounding device connected to the database, wherein the sounding device sends out various types of prompt tones according to a comparative result from the face recognition module.

13. The image recognition method as claimed in claim 8 , further comprising: making a determination that an image feature information of the face image is incompatible with the image feature information of the known identity; and based on the determination, repeating steps (a)-(c).

14. The image recognition method as claimed in claim 9 , further comprising: making a determination that an image feature information of the face image is incompatible with the image feature information of the known identity; and based on the determination, repeating steps (a)-(c).

15. The image recognition method as claimed in claim 10 , further comprising: making a determination that an image feature information of the face image is incompatible with the image feature information of the known identity; and based on the determination, repeating steps (a)-(c).

16. The image recognition method as claimed in claim 11 , further comprising: making a determination that an image feature information of the face image is incompatible with the image feature information of the known identity; and based on the determination, repeating steps (a)-(c).

17. The image recognition method as claimed in claim 8 , further comprising: making a determination that an image feature information of the face image is incompatible with the image feature information of the known identity; and based on the determination, repeating steps (a)-(c).

18. The image recognition method as claimed in claim 12 , further comprising: making a determination that an image feature information of the face image is incompatible with the image feature information of the known identity; and based on the determination, repeating steps (a)-(c).